S3FCD: a single-temporal self-supervised learning framework for remote sensing image change detection

Change detection is a crucial technique for identifying change information between image pairs of the same geographical area. Existing deep learning-based change detection methods achieve high performance by utilizing annotated and registered bi-temporal images. However, obtaining accurate annotations and registered bi-temporal images requires expert knowledge and substantial financial resources. The effectiveness of models may be constrained by the limited variation scenarios within available change detection datasets. To address these issues, we develop a novel single-temporal self-supervised learning framework for change detection, namely S3FCD, which facilitates training a bi-temporal remote sensing image change detection model without labeled and registered paired data. Specifically, a coarse change generator is first employed to generate pairs of training data for training a preliminary change detection model. To improve the quality of the generated image pairs, a deep feature-based generator (DFG) module is designed based on the pre-trained model. To enhance the diversity of the generated image pairs, a patch memory bank (PMB) module is integrated into DFG for storing and managing patches. S3FCD has demonstrated state-of-the-art performance across multiple datasets.